46 citations · 102 across the 9 of their papers we have counts for
11 papers
Communication between Frozen Large Language Models via Prompt Optimization in a Referential Game
Vivek Anand, Muthu Chandrasekaran, Shiva Chaitanya
We study communication between two frozen large language models from different providers, with different tokenizers, accessed through their API endpoints. The two play a referentia…
Read Top News First: A Document Reordering Approach for Multi-Document News Summarization
Chao Zhao, Tenghao Huang, Somnath Basu Roy Chowdhury +3
A common method for extractive multi-document news summarization is to re-formulate it as a single-document summarization problem by concatenating all documents as a single meta-do…
Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings
Kailash Karthik Saravanakumar, Miguel Ballesteros, Muthu Kumar Chandrasekaran +1
We propose a method for online news stream clustering that is a variant of the non-parametric streaming K-means algorithm. Our model uses a combination of sparse and dense document…
The CL-SciSumm Shared Task 2018: Results and Key Insights
Kokil Jaidka, Michihiro Yasunaga, Muthu Kumar Chandrasekaran +2
This overview describes the official results of the CL-SciSumm Shared Task 2018 -- the first medium-scale shared task on scientific document summarization in the computational ling…
Overview and Results: CL-SciSumm Shared Task 2019
Muthu Kumar Chandrasekaran, Michihiro Yasunaga, Dragomir Radev +2
The CL-SciSumm Shared Task is the first medium-scale shared task on scientific document summarization in the computational linguistics~(CL) domain. In 2019, it comprised three task…
When to reply? Context Sensitive Models to Predict Instructor Interventions in MOOC Forums
Muthu Kumar Chandrasekaran, Min-Yen Kan
Due to time constraints, course instructors often need to selectively participate in student discussion threads, due to their limited bandwidth and lopsided student--instructor rat…
Report on the 3rd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2018)
Philipp Mayr, Muthu Kumar Chandrasekaran, Kokil Jaidka
The joint BIRNDL workshop was held at the 41st ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2018) in Ann Arbor, USA. BIRNDL 2018 intend…
Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2017)
Muthu Kumar Chandrasekaran, Kokil Jaidka, Philipp Mayr
The large scale of scholarly publications poses a challenge for scholars in information seeking and sensemaking. Bibliometrics, information retrieval (IR), text mining and NLP tech…
Using Discourse Signals for Robust Instructor Intervention Prediction
Muthu Kumar Chandrasekaran, Carrie Demmans Epp, Min-Yen Kan +1
We tackle the prediction of instructor intervention in student posts from discussion forums in Massive Open Online Courses (MOOCs). Our key finding is that using automatically obta…
A Comparison of Word Embeddings for English and Cross-Lingual Chinese Word Sense Disambiguation
Hong Jin Kang, Tao Chen, Muthu Kumar Chandrasekaran +1
Word embeddings are now ubiquitous forms of word representation in natural language processing. There have been applications of word embeddings for monolingual word sense disambigu…
Learning Instructor Intervention from MOOC Forums: Early Results and Issues
Muthu Kumar Chandrasekaran, Min-Yen Kan, Bernard C. Y. Tan +1
With large student enrollment, MOOC instructors face the unique challenge in deciding when to intervene in forum discussions with their limited bandwidth. We study this problem of…